Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    valuable

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crowd
    0.40
    St
    0.39
    higher
    0.39
    ボトル
    0.38
     सह
    0.38
    ST
    0.37
     red
    0.37
     ټ
    0.36
    red
    0.36
    Red
    0.35
    POSITIVE LOGITS
     asset
    1.73
     Asset
    1.49
    资产
    1.40
    Asset
    1.38
    asset
    1.38
     assets
    1.28
     Assets
    1.20
    assets
    1.16
    Assets
    1.09
    資産
    1.07
    Act Density 0.001%

    No Known Activations